Neural Causal Models

Recording

Deep neural networks have achieved outstanding success in many tasks ranging from computer vision, to natural language processing, and robotics. However such models still pale in their ability to understand the world around us, as well as generalizing and adapting to new tasks or environments. One possible solution to this problem are causal models, since they can reason about the connections between causal variables and the effect of intervening on them. However, existing algorithms for learning causal graphs from data are often having exponential cost both with the number of variables or the number of observations. This talk will introduce the fundamental concepts of causal inference, connections and synergies with deep learning as well as practical applications and advances in sustainability and AI for science.

Stefan Bauer is an Assistant Professor at KTH Stockholm, affiliated with the Wallenberg AI, Autonomous Systems and Software Program (WASP) and a CIFAR Azrieli Global Scholar. Before that he was a research group leader at the MPI for Intelligent Systems.

Using and developing tools of causality and deep learning, his research focuses on the longstanding goal of artificial intelligence to design machines that can extrapolate experience across environments and tasks. He obtained his PhD in Computer Science from ETH Zurich and was awarded with the ETH medal for an outstanding doctoral thesis. Before that, he graduated with a BSc and MSc in Mathematics from ETH Zurich and a BSc in Economics and Finance from the University of London (LSE). During his studies, he held scholarships from the Swiss and German National Merit Foundation. In 2019, he won the best paper award at the International Conference of Machine Learning (ICML) and in 2020 and 2021, he was the lead organizer of the real-robot-challenge.com, a robotics challenge in the cloud.

Beyond robotics, the research group focuses on health and biomedical AI applications. For example we analyzed 70k patients across 70 hospitals in the US and Europe for real-time COVID-19 related mortality prediction (CovEWS Score in Nature Communications, 2021) or created enabling tools like web platforms for high-throughput analysis of sleep patterns, which are used daily by academic and industrial researchers worldwide.